Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    t followed by ingle, ension, enses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ravel
    0.83
    nT
    0.75
    fetchall
    0.73
    udy
    0.73
    iktok
    0.72
    ifi
    0.71
    ialis
    0.70
    ğrafl
    0.70
    ahun
    0.69
    ífica
    0.69
    POSITIVE LOGITS
     gah
    0.70
     veteran
    0.69
     Ding
    0.69
    әм
    0.69
    щаться
    0.69
     Chast
    0.68
    鐐
    0.67
    पन
    0.67
     swo
    0.66
     guilt
    0.66
    Act Density 0.018%

    No Known Activations